SaaS-Bench - Team Collaboration and Document Workflow: leaderboard

SaaS-Bench (2026) evaluates computer-use agents on long professional workflows across 23 self-hosted SaaS systems, scoring weighted verification checkpoints on the final application state. This board is the checkpoint score in percent on the team collaboration and document workflow domain; higher is better.

Metric: Checkpoint score (%) on the team collaboration and document workflow domain, weighted-checkpoint score over the final application states, browser-use agent loop over live self-hosted SaaS apps (DOM and screenshot observations, restricted browser actions, no JavaScript or backend access), same step budget, timeout and failure cap for every model; higher is better. Source: arxiv.org. Saturation forecast: Around September 2027. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 4.665.2#113
2GPT-5.5High54.6#54
3GPT-5.4High50.4#135
4Kimi K2.548.4#266
5Gemini 3.1 Pro (Preview)48.2#99
6Claude Opus 4.747.7#85
7Kimi K2.647.2#192
8Qwen 3.6 Plus44.6#238
9DeepSeek V4 Pro39.4#196
10GLM-5.139#198
11Seed 2.0 Pro33.2#222
12MiniMax-M2.729.9#539
13Gemini 3.5 FlashHigh15.7#106
14Claude Sonnet 4.615.2#173

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=saas-bench-team-collaboration-and-document-workflow · How It Works · Data refreshed daily, snapshot 2026-11-21.